© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10749
    Prev
    Next
    INDEX
    Explanations

    now, let's

    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
    на
    2.77
    '
    2.49
    นน
    2.05
    ',
    2.03
    s
    1.98
     ('
    1.95
    pire
    1.85
    sia
    1.80
    吻
    1.79
    т
    1.79
    POSITIVE LOGITS
    धारी
    1.88
     nodo
    1.77
    Ĕ
    1.76
    baar
    1.74
    бто
    1.74
    র্তি
    1.71
    atihan
    1.70
    𝚍
    1.68
     combinado
    1.65
     huidige
    1.64
    Activations Density 0.010%

    No Known Activations