© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 708
    Prev
    Next
    INDEX
    Explanations

    with explanations

    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
    ara
    0.41
    lensFlare
    0.37
    InfoPlist
    0.36
    RawContext
    0.36
    er
    0.35
     =
    0.35
    meldung
    0.35
    jenigen
    0.35
    iation
    0.34
    ider
    0.34
    POSITIVE LOGITS
     no
    0.53
     considerable
    0.50
    ی
    0.49
     a
    0.49
     respect
    0.48
     கூடிய
    0.47
     potencial
    0.46
     gusto
    0.46
     ulterior
    0.46
     impunity
    0.45
    Activations Density 0.354%

    No Known Activations