© 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. 77055
    Prev
    Next
    INDEX
    Explanations

    capabilities and technologies

    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
    눠
    0.51
    altra
    0.47
    häng
    0.47
     умолча
    0.47
    }
    0.45
     аутох
    0.45
    ຮູ້
    0.45
     দেয়া
    0.44
    ický
    0.44
     opcion
    0.44
    POSITIVE LOGITS
     capabilities
    0.46
     kapasitas
    0.46
     squares
    0.45
     conferences
    0.45
     rivets
    0.45
     Capabilities
    0.44
     spheres
    0.43
     kpc
    0.43
     lanes
    0.42
     –
    0.42
    Activations Density 0.000%

    No Known Activations