© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14134
    Prev
    Next
    INDEX
    Explanations

    $ redirection

    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
    𝙜
    2.88
    g
    2.54
    𝙩
    2.46
    ToProps
    2.44
    𝒚
    2.38
    anic
    2.35
    𝒈
    2.35
     ske
    2.33
    uvi
    2.31
    𝙘
    2.29
    POSITIVE LOGITS
     eyebrows
    2.05
    yeong
    2.01
    illiams
    1.98
    嬛
    1.97
    กรม
    1.96
    ூரில்
    1.93
    ··
    1.92
    тие
    1.91
     ·
    1.91
    stin
    1.91
    Activations Density 0.006%

    No Known Activations