© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2422
    Prev
    Next
    INDEX
    Explanations

    free verse, speech, code, area

    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_22_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
    Recogn
    0.83
    Yb
    0.83
    dı
    0.79
    ன்
    0.78
    紳
    0.76
    蜜
    0.76
    mér
    0.75
    শ
    0.75
    nahi
    0.74
     Gather
    0.74
    POSITIVE LOGITS
    bies
    1.92
    bie
    1.79
    zing
    1.40
    zers
    1.37
     reign
    1.12
    ZE
    1.10
    🆓
    1.07
    floating
    1.06
    zer
    1.04
    bees
    1.03
    Activations Density 0.145%

    No Known Activations