© 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. 20088
    Prev
    Next
    INDEX
    Explanations

    Energy conservation and efficiency

    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
     případě
    0.43
    琇
    0.43
    ઠવા
    0.42
    ధిక
    0.41
     рецеп
    0.41
    тами
    0.41
    τι
    0.40
    规律
    0.40
    光谱
    0.40
    🏷
    0.40
    POSITIVE LOGITS
     imperfections
    0.46
     imperfection
    0.43
     obstru
    0.43
     interoper
    0.42
     Neander
    0.40
     Nemours
    0.40
     annihil
    0.40
    inus
    0.40
    it
    0.39
     interdependence
    0.39
    Activations Density 0.001%

    No Known Activations