© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 64402
    Prev
    Next
    INDEX
    Explanations

    accumulates / incremental / compressed / reversed / output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     civil
    0.47
     inf
    0.40
     l
    0.40
     karaoke
    0.39
     remake
    0.39
     rein
    0.38
     Karaoke
    0.38
    ustos
    0.38
     Monst
    0.38
    зацию
    0.38
    POSITIVE LOGITS
    ąpi
    0.46
     accumulates
    0.45
     Accum
    0.42
    IVIDUAL
    0.42
    Accum
    0.42
    individual
    0.41
    ../../
    0.39
     गंभीरता
    0.38
    Individual
    0.38
    蕴
    0.38
    Activations Density 0.001%

    No Known Activations