© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7481
    Prev
    Next
    INDEX
    Explanations

    e followed by ee or rotic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    zka
    0.66
    ników
    0.63
     допъл
    0.62
    quierda
    0.61
    者が
    0.61
     ಹೆಚ್ಚ
    0.59
    ✮
    0.58
    𝘫
    0.57
    ainen
    0.56
    ᴏ
    0.56
    POSITIVE LOGITS
     coli
    0.82
    coli
    0.70
    ITHER
    0.66
    南北
    0.57
     Scrooge
    0.56
     Eo
    0.56
     ஈ
    0.55
     E
    0.53
     Majorana
    0.53
     smtp
    0.53
    Activations Density 0.240%

    No Known Activations