© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14289
    Prev
    Next
    INDEX
    Explanations

    risk, tort, novel, encryption, deductive

    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_13_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
    isuus
    1.34
    ărat
    1.23
    ي
    1.22
     soprattutto
    1.16
    también
    1.15
    oría
    1.13
    bours
    1.11
    rison
    1.11
    imamente
    1.11
    ánico
    1.11
    POSITIVE LOGITS
     열심히
    1.73
     やっ
    1.72
    ینڈ
    1.71
     명
    1.70
     返回
    1.70
     구
    1.70
    어서
    1.69
     패
    1.69
     getLast
    1.69
     Oops
    1.68
    Activations Density 0.000%

    No Known Activations