© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9627
    Prev
    Next
    INDEX
    Explanations

    LEGOs fit together

    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_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
    敗
    0.43
     bulan
    0.41
    年間
    0.41
     Wochen
    0.41
     erkannt
    0.40
    細胞
    0.40
     maanden
    0.40
     weken
    0.40
     unver
    0.39
     Monate
    0.39
    POSITIVE LOGITS
     explanations
    0.48
    os
    0.47
    om
    0.45
     القد
    0.45
    фикации
    0.45
    𝕌
    0.44
     bonuses
    0.44
     housings
    0.44
    amask
    0.44
     captions
    0.44
    Activations Density 0.000%

    No Known Activations