© 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-65K
    7. 568
    Prev
    Next
    INDEX
    Explanations

    invitations to ask or act

    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_65k_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
     was
    0.94
     is
    0.92
    0.91
     has
    0.88
    an
    0.86
    hy
    0.78
    was
    0.75
    hum
    0.75
    a
    0.73
     contains
    0.72
    POSITIVE LOGITS
    <unused1398>
    1.40
    <unused1465>
    1.40
    <unused1294>
    1.40
    <unused1289>
    1.39
    𐰽
    1.39
    <unused1464>
    1.38
    <unused1497>
    1.38
     trataro
    1.37
    <unused1293>
    1.37
    KeepOriginal
    1.37
    Activations Density 0.106%

    No Known Activations