© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6953
    Prev
    Next
    INDEX
    Explanations

    voiceover and vocal descriptors

    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_22_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
    叩
    0.97
    skich
    0.95
     voetbal
    0.92
     flanking
    0.90
    duled
    0.86
    schaft
    0.86
     kick
    0.83
    踢
    0.83
    emuan
    0.81
    ്ല
    0.81
    POSITIVE LOGITS
     MAIL
    1.14
    MAIL
    1.09
     mail
    1.06
     mails
    1.02
    mail
    0.98
    톤
    0.94
     inflection
    0.93
    Attorney
    0.92
     krat
    0.92
     Mail
    0.92
    Activations Density 0.078%

    No Known Activations