© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5295
    Prev
    Next
    INDEX
    Explanations

    not when script imported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为你
    0.86
     deveria
    0.83
     loving
    0.74
     assuntos
    0.73
    /+
    0.73
     wouldn
    0.72
    性和
    0.71
     serían
    0.71
     estaría
    0.71
     sería
    0.70
    POSITIVE LOGITS
    riction
    0.72
     neutrophils
    0.70
    wiąz
    0.70
    зец
    0.69
    iktok
    0.68
    rapolation
    0.68
     অবজার
    0.68
     নত
    0.67
     Barra
    0.67
    ቧ
    0.66
    Activations Density 0.060%

    No Known Activations