© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15286
    Prev
    Next
    INDEX
    Explanations

    issues, problems, crime

    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_13_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
     একটী
    0.88
     Giving
    0.81
    一
    0.81
     Extra
    0.80
     One
    0.80
    也
    0.80
    会
    0.79
     )),
    0.79
     Talks
    0.78
     Offering
    0.78
    POSITIVE LOGITS
     transacción
    0.87
     peligros
    0.85
     línea
    0.84
     explotación
    0.82
     koriste
    0.82
     válv
    0.80
     protesta
    0.79
     tolerancia
    0.79
     utilización
    0.78
     ██
    0.78
    Activations Density 0.000%

    No Known Activations