© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15544
    Prev
    Next
    INDEX
    Explanations

    children and babies

    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
     and
    1.12
    '
    1.09
    ’
    1.08
    gift
    1.01
     brothers
    0.99
     sister
    0.98
    ette
    0.96
    hip
    0.96
    old
    0.95
     who
    0.95
    POSITIVE LOGITS
     visant
    1.63
     egyéb
    1.48
     zuletzt
    1.47
     vozila
    1.46
    ⊔
    1.46
    AuditEvent
    1.44
     기능을
    1.43
    詬
    1.42
     로그
    1.42
     구간
    1.41
    Activations Density 0.114%

    No Known Activations