© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3419
    Prev
    Next
    INDEX
    Explanations

    hovering over, options, responses

    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
    Per
    0.66
    L
    0.56
     Profil
    0.55
    Pal
    0.54
    P
    0.54
    untuk
    0.53
     Per
    0.53
    Re
    0.51
    Is
    0.50
    Se
    0.49
    POSITIVE LOGITS
     worrying
    0.60
     boiling
    0.60
     affecting
    0.56
     affect
    0.55
    వే
    0.54
     intensify
    0.54
     boiled
    0.54
    \_
    0.54
     intensified
    0.53
     angered
    0.53
    Activations Density 0.000%

    No Known Activations