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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 14259
    Prev
    Next
    INDEX
    Explanations

    central european places and cossacks

    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
    ôle
    0.57
    Bankr
    0.52
    íst
    0.52
     friendliness
    0.51
     ह
    0.50
    ück
    0.49
    </h1>
    0.49
     بھارت
    0.49
     ضمن
    0.48
    ôté
    0.48
    POSITIVE LOGITS
    AL
    0.71
    pm
    0.58
    AS
    0.57
    IS
    0.56
    جري
    0.56
    AR
    0.54
    рте
    0.54
    р
    0.54
     mne
    0.54
     Elkus
    0.53
    Activations Density 0.029%

    No Known Activations