© 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. 14533
    Prev
    Next
    INDEX
    Explanations

    beliefs

    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
    দ্ম
    2.64
    
    2.56
    \%
    2.52
     \]
    2.52
    ειο
    2.51
    ει
    2.49
    
    2.48
    ]}\
    2.47
    ]</
    2.46
    \'
    2.45
    POSITIVE LOGITS
    leş
    2.95
    lela
    2.79
    enzen
    2.69
    ozo
    2.67
     mn
    2.53
    gub
    2.52
     Egyes
    2.51
    ligen
    2.50
    త్మిక
    2.48
    بات
    2.42
    Activations Density 0.167%

    No Known Activations