© 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. 31-GEMMASCOPE-2-RES-262K
    7. 79081
    Prev
    Next
    INDEX
    Explanations

    generating fake words

    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/layer_31_width_262k_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
    up
    0.46
     and
    0.44
     Fortress
    0.43
     New
    0.43
    ư
    0.42
     The
    0.42
    c
    0.41
    highly
    0.41
     an
    0.41
    e
    0.40
    POSITIVE LOGITS
     resonances
    0.47
     spinors
    0.46
     resonance
    0.42
     isotropy
    0.42
     compost
    0.42
    ریشن
    0.41
     strept
    0.40
     copolymers
    0.40
     resonators
    0.40
     magnetores
    0.39
    Activations Density 0.000%

    No Known Activations