© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 117523
    Prev
    Next
    INDEX
    Explanations

    easiest to more complex

    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
     a
    0.53
     सिंगापुर
    0.47
    年
    0.46
    '
    0.46
    㐄
    0.46
     an
    0.45
    ester
    0.44
    http
    0.44
     Singapore
    0.43
    ायक
    0.43
    POSITIVE LOGITS
     effettuare
    0.51
     eseguire
    0.50
    >(&
    0.48
     linguistique
    0.47
     effectué
    0.47
    ρούν
    0.47
     culturel
    0.45
     περί
    0.45
    গৃহ
    0.45
    行う
    0.45
    Activations Density 0.003%

    No Known Activations