© 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. 11676
    Prev
    Next
    INDEX
    Explanations

    historical dates and facts

    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
    ized
    3.21
    ised
    2.60
    𝗸
    2.57
    ity
    2.47
    ization
    2.46
    ism
    2.38
     la
    2.31
    𝘇
    2.29
    𝗹
    2.26
    ov
    2.25
    POSITIVE LOGITS
    ProductRunnable
    2.81
    ടുന്ന
    2.70
     PluginResult
    2.65
     fonctionnal
    2.64
     CallOptions
    2.60
    鈳
    2.58
     Cuenta
    2.53
    ぇ
    2.46
     "\(
    2.43
     Autres
    2.41
    Activations Density 0.000%

    No Known Activations