© 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. 70960
    Prev
    Next
    INDEX
    Explanations

    AI ethics & historical sensitivity

    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
    onesome
    0.48
    模仿
    0.44
    耻
    0.42
    postdata
    0.41
     نسبة
    0.41
    መሳሳይ
    0.40
    зец
    0.40
    成为
    0.40
    <0xB6>
    0.40
    />}/>
    0.40
    POSITIVE LOGITS
     Babe
    0.43
     Administration
    0.42
     Exist
    0.42
    unii
    0.42
     Existence
    0.41
     Investor
    0.41
     Industri
    0.41
    B
    0.40
     exists
    0.40
     exist
    0.40
    Activations Density 0.065%

    No Known Activations