© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3820
    Prev
    Next
    INDEX
    Explanations

    events and actions

    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_7_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
     вино
    1.81
     andRow
    1.72
    
    1.70
     socalled
    1.65
    𒇫
    1.64
     andDevice
    1.60
     SNP
    1.58
    𒐸
    1.55
    <unused1957>
    1.54
     RBI
    1.54
    POSITIVE LOGITS
    P
    1.53
    إ
    1.24
     P
    1.20
    أ
    1.19
    L
    1.18
    П
    1.17
    शील
    1.16
    J
    1.08
    Č
    1.07
    أم
    1.06
    Activations Density 0.205%

    No Known Activations