© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79191
    Prev
    Next
    INDEX
    Explanations

    conspiracy, flammable, brand positioning, future market

    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
    w
    0.59
     new
    0.53
    r
    0.50
     buy
    0.48
    g
    0.47
    v
    0.46
    x
    0.46
    z
    0.46
     download
    0.43
     normalized
    0.43
    POSITIVE LOGITS
     tiennent
    0.56
    ปาก
    0.46
    食品
    0.46
    䍩
    0.45
    肐
    0.44
    াপ
    0.44
    Could
    0.43
    旲
    0.43
    陂
    0.43
    䏍
    0.43
    Activations Density 0.003%

    No Known Activations