© 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. 65110
    Prev
    Next
    INDEX
    Explanations

    ongoing tasks and changes

    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
    ешься
    0.57
    क्का
    0.56
    юсь
    0.47
     心
    0.46
     сердце
    0.46
    心を
    0.46
    τά
    0.45
    álen
    0.42
     εν
    0.42
     `:`
    0.42
    POSITIVE LOGITS
     assignment
    0.48
     organi
    0.48
     arrang
    0.47
     arranger
    0.47
     associative
    0.46
     Casc
    0.43
    Casc
    0.43
    长安
    0.43
     nasled
    0.42
    dimensioni
    0.42
    Activations Density 0.008%

    No Known Activations