© 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. 113330
    Prev
    Next
    INDEX
    Explanations

    assuming proceeding confirmed

    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
     abusive
    0.46
    fre
    0.44
    typed
    0.43
    graded
    0.42
     intimidating
    0.42
     rejected
    0.42
    differential
    0.42
    ₹
    0.42
    capt
    0.42
    professional
    0.42
    POSITIVE LOGITS
     যতদিন
    0.46
     پارک
    0.44
     Closeup
    0.44
     textes
    0.44
     Dunes
    0.43
     Crossroads
    0.43
    ayanan
    0.42
     forêts
    0.42
     Pocket
    0.42
     Trails
    0.41
    Activations Density 0.009%

    No Known Activations