© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146484
    Prev
    Next
    INDEX
    Explanations

    moksha and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     barking
    0.73
     क्विक
    0.73
     Ve
    0.72
    ᐈ
    0.72
    モチ
    0.70
     flocked
    0.69
     هيك
    0.68
     ruk
    0.67
     harp
    0.67
    万人
    0.65
    POSITIVE LOGITS
    Around
    0.68
     tarde
    0.68
     দি
    0.66
    Here
    0.64
    𝗡
    0.64
    classical
    0.64
    bumptech
    0.64
    পশ্চ
    0.63
    Blocks
    0.63
    Classical
    0.63
    Activations Density 0.001%

    No Known Activations