© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12582
    Prev
    Next
    INDEX
    Explanations

    difficulties on the spruce

    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
    '.
    1.01
     realises
    0.89
    ".
    0.89
    raises
    0.89
    ?.
    0.86
    :-
    0.86
    ‌.
    0.83
    _.
    0.82
    ‐
    0.82
    ,.
    0.81
    POSITIVE LOGITS
     변화
    1.25
    ёд
    1.22
    šenja
    1.16
    ストレス
    1.16
     آہ
    1.15
    ืด
    1.15
     inefficiencies
    1.13
    危害
    1.12
     inclement
    1.12
     downtime
    1.12
    Activations Density 0.015%

    No Known Activations