© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6752
    Prev
    Next
    INDEX
    Explanations

    Okay, providing information

    np_acts-logits-general · gemini-2.5-flash-lite

    Tokens marking the model/assistant's turn (i.e., the start or label of the model's generated reply).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tweaking
    0.48
     addirittura
    0.47
     tweaks
    0.45
     booze
    0.44
    屇
    0.42
     bici
    0.41
     Spannung
    0.41
     vess
    0.41
     spannend
    0.41
    摒
    0.39
    POSITIVE LOGITS
     informatie
    0.57
    信息
    0.53
    information
    0.52
    一般的な
    0.52
     information
    0.51
     जानकारी
    0.51
     informazioni
    0.50
     பொதுவாக
    0.50
     информацию
    0.49
     ಮಾಹಿತಿ
    0.48
    Activations Density 2.291%

    No Known Activations