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

    Neuronpedia

    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. 33459
    Prev
    Next
    INDEX
    Explanations

    warnings and basic facts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    natal
    0.42
    _
    0.42
    eri
    0.41
    ekten
    0.41
    AE
    0.40
    ekt
    0.40
    BA
    0.40
    rogen
    0.39
    Liv
    0.39
    BS
    0.39
    POSITIVE LOGITS
     ਤੁਸੀਂ
    0.47
     馬
    0.46
     horseback
    0.46
    തി
    0.44
    žete
    0.44
    หมือน
    0.44
     gouvernement
    0.43
    permitted
    0.43
     మీరు
    0.42
     Uttar
    0.42
    Activations Density 0.005%

    No Known Activations