© 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. 40068
    Prev
    Next
    INDEX
    Explanations

    after or before phrases

    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
     popula
    0.44
     berühm
    0.44
     哈
    0.44
     masterpiece
    0.44
    韫
    0.44
     costruito
    0.43
    ദേ
    0.42
    CreateCharacter
    0.42
     кро
    0.42
     Gemä
    0.42
    POSITIVE LOGITS
    /
    0.42
     personalized
    0.40
     almeno
    0.38
     customization
    0.38
     susceptibility
    0.38
     exemptions
    0.37
    ོས་
    0.37
     discounts
    0.37
     vials
    0.37
     infractions
    0.37
    Activations Density 0.014%

    No Known Activations