© 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. 16-GEMMASCOPE-2-RES-262K
    4. 35130
    Prev
    Next
    INDEX
    Explanations

    saving time accessing

    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_16_width_262k_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
    Ссы
    0.59
    KOH
    0.52
     neoplas
    0.52
    ಶ್ರೀ
    0.51
    ر
    0.51
    promo
    0.51
    type
    0.50
    }$.
    0.50
    Prema
    0.50
    ID
    0.50
    POSITIVE LOGITS
    ానిక
    0.46
    andered
    0.43
    '
    0.43
     ওমর
    0.43
    目は
    0.42
     Félix
    0.42
     Charity
    0.41
     Whisper
    0.41
    স্থানের
    0.41
     Bing
    0.41
    Activations Density 0.000%

    No Known Activations