© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63774
    Prev
    Next
    INDEX
    Explanations

    ® symbol, legal terms, specific actions

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

    STIs, therapies, pattern generation, routine, tracking

    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
    the
    0.69
    ли
    0.59
    3
    0.55
    there
    0.54
    les
    0.54
    very
    0.50
    Thirty
    0.47
    sw
    0.47
    lem
    0.47
     Democracy
    0.47
    POSITIVE LOGITS
     strumenti
    0.51
     embold
    0.49
     underm
    0.48
    ┑
    0.48
    SpawnEntry
    0.48
     nást
    0.47
     enquanto
    0.46
    HasFieldError
    0.45
     duckys
    0.45
     instrumentos
    0.45
    Activations Density 0.000%

    No Known Activations