© 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. 7815
    Prev
    Next
    INDEX
    Explanations

    help me tailor

    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
    rs
    1.17
    ociaż
    1.02
    issant
    1.00
    lp
    0.96
     cih
    0.95
    oden
    0.95
     flair
    0.93
    汁
    0.92
    óz
    0.92
    ɽ
    0.91
    POSITIVE LOGITS
     harbor
    1.35
     Harbor
    1.26
     harbours
    1.23
     harbors
    1.22
     harbour
    1.20
     deposit
    1.19
     guarding
    1.13
     nets
    1.13
     Harbour
    1.12
    deposit
    1.09
    Activations Density 0.085%

    No Known Activations