© 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. 2982
    Prev
    Next
    INDEX
    Explanations

    988 in

    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
    ರಿಸ
    0.40
     alimento
    0.37
     άλλα
    0.37
     ವಿಶೇಷ
    0.36
     substituents
    0.35
     ISIS
    0.34
     arrhyth
    0.33
    謢
    0.33
     rainfall
    0.33
     legít
    0.33
    POSITIVE LOGITS
    It
    0.39
    on
    0.37
    Join
    0.35
    èbre
    0.35
    क
    0.35
    Give
    0.34
    Founded
    0.34
    のような
    0.34
     शाहिद
    0.34
    Listen
    0.34
    Activations Density 0.086%

    No Known Activations