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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101036
    Prev
    Next
    INDEX
    Explanations

    removing both, direct inspiration, text-to-speech

    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
    श्न
    0.49
    莗
    0.48
     Workers
    0.45
     Literally
    0.45
     Payload
    0.45
    াস
    0.44
     rationally
    0.44
     :=\
    0.44
    螈
    0.44
    規範
    0.43
    POSITIVE LOGITS
    aptop
    0.49
    vorschau
    0.49
    arger
    0.47
    VIDOR
    0.45
    License
    0.45
    gifts
    0.45
    vorsch
    0.44
    coon
    0.43
    olok
    0.43
    Colorful
    0.43
    Activations Density 0.001%

    No Known Activations