© 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. 7-GEMMASCOPE-2-RES-16K
    7. 153
    Prev
    Next
    INDEX
    Explanations

    personal space

    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
     is
    1.48
    2
    1.40
     was
    1.37
    1
    1.36
    4
    1.34
     The
    1.34
     has
    1.32
    3
    1.30
    9
    1.30
     gives
    1.29
    POSITIVE LOGITS
     cosidd
    1.85
    兟
    1.77
    𒀯
    1.77
     filóso
    1.76
    𒆤
    1.75
     atteggi
    1.72
    𒀊
    1.72
     Usuarios
    1.69
    侸
    1.68
    𒌦
    1.68
    Activations Density 0.703%

    No Known Activations