© 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. 8237
    Prev
    Next
    INDEX
    Explanations

    enthusiastic tone

    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
    iph
    0.49
     Exceptions
    0.46
    ocaps
    0.46
    volvimento
    0.44
    WR
    0.42
    らしい
    0.41
    âncias
    0.40
    ﻟ
    0.40
    ・
    0.39
    Exceptions
    0.39
    POSITIVE LOGITS
    yas
    0.53
     inscriptions
    0.52
     inds
    0.52
     adulter
    0.51
     unmist
    0.49
     ဆို
    0.49
     suffixes
    0.49
     nucleotides
    0.49
     inscribed
    0.49
     angered
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.