© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5746
    Prev
    Next
    INDEX
    Explanations

    draining life force

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ṓ
    1.39
    _:
    1.33
    čin
    1.32
    ⵓ
    1.31
     váš
    1.31
    ِّ
    1.30
    ❖
    1.29
    áž
    1.29
    ēr
    1.28
    ⌋
    1.28
    POSITIVE LOGITS
    墾
    1.05
     gas
    1.05
     devono
    1.04
    емости
    1.03
    hm
    1.02
     Sudden
    1.02
     and
    1.01
     Def
    1.00
     टीवी
    0.99
     saranno
    0.98
    Activations Density 0.000%

    No Known Activations