© 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-65K
    7. 4116
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind

    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_65k_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
     }{\
    0.42
    EnableWeb
    0.41
     carénés
    0.41
    ？](
    0.38
     خاصة
    0.38
    dí
    0.38
     জু
    0.38
    阅
    0.38
     UVA
    0.38
     fonctionnalité
    0.38
    POSITIVE LOGITS
    TE
    0.47
    PE
    0.46
     behest
    0.46
    volving
    0.45
    CE
    0.44
    ochen
    0.43
    Bey
    0.42
    CH
    0.42
    ಗೆ
    0.42
     churning
    0.41
    Activations Density 0.064%

    No Known Activations