© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 6057
    Prev
    Next
    INDEX
    Explanations

    programming language const declarations

    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_16k_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
    )^{*
    0.59
     придется
    0.54
    issä
    0.51
    )))
    0.50
    θεί
    0.49
    начала
    0.48
    )\,
    0.48
     clocked
    0.48
    টা
    0.47
    ):=
    0.47
    POSITIVE LOGITS
     immutable
    0.68
    as
    0.66
     admire
    0.56
     for
    0.54
    immutable
    0.54
     by
    0.53
    os
    0.52
     unchanging
    0.52
     inspire
    0.52
     infus
    0.49
    Activations Density 0.089%

    No Known Activations