© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218819
    Prev
    Next
    INDEX
    Explanations

    wherein clauses and subsequent details

    np_acts-logits-general · gemini-2.5-flash-lite

    asking questionspastessimpler expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    щото
    0.49
    Drops
    0.46
    DURATION
    0.42
    Routine
    0.41
    褥
    0.41
    ”)
    0.40
    ”
    0.40
    Npm
    0.40
    PathResource
    0.40
    胧
    0.40
    POSITIVE LOGITS
    g
    0.52
     Eritrea
    0.52
     ЕС
    0.51
    p
    0.50
    mex
    0.48
     ESO
    0.47
    j
    0.47
     អ
    0.47
    bout
    0.47
     अर्जेंटीना
    0.47
    Activations Density 0.002%

    No Known Activations