© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8995
    Prev
    Next
    INDEX
    Explanations

    interfering with, stopped counting, introduce new

    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
    7
    1.11
     In
    1.08
    In
    1.03
    who
    1.01
    8
    0.99
    how
    0.98
     US
    0.96
    6
    0.93
     who
    0.92
    sub
    0.92
    POSITIVE LOGITS
    pieceSelection
    1.55
    ៀប
    1.55
    mektedir
    1.44
    ılıyor
    1.44
     barbecue
    1.43
    𒄩
    1.37
    wallepics
    1.36
    <unused591>
    1.36
    ılmıştır
    1.35
     endExpNow
    1.35
    Activations Density 0.000%

    No Known Activations