© 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. 533
    Prev
    Next
    INDEX
    Explanations

    short + content request

    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
    2
    2.05
    1
    1.98
     the
    1.89
    4
    1.87
    1.85
    3
    1.82
    9
    1.80
    0
    1.78
    5
    1.77
    6
    1.74
    POSITIVE LOGITS
    okatokat
    3.29
     kahelar
    3.20
    𒍝
    3.20
    𒀖
    3.17
    𒌦
    3.15
    𒌵
    3.15
     Pusenkoff
    3.14
    𒀯
    3.12
    𒈣
    3.12
     filóso
    3.11
    Activations Density 0.071%

    No Known Activations