© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8592
    Prev
    Next
    INDEX
    Explanations

    master encouraging exploitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     (
    0.86
     no
    0.84
    }}[
    0.83
     force
    0.82
    ont
    0.81
    bel
    0.80
     uh
    0.80
     saman
    0.78
     Force
    0.78
     التق
    0.77
    POSITIVE LOGITS
    🤍
    1.16
     tumours
    1.14
     ♡
    1.14
    рім
    1.12
     ホイール
    1.12
     SeekBar
    1.09
    筥
    1.05
    combo
    1.04
    kę
    1.03
    ޓ
    1.02
    Activations Density 0.000%

    No Known Activations