© 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. 123769
    Prev
    Next
    INDEX
    Explanations

    average out the cost

    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
     rematch
    0.46
     bulge
    0.44
    edad
    0.43
     reverting
    0.43
    u
    0.42
    eto
    0.40
    alee
    0.40
    bod
    0.39
     flexing
    0.39
     variable
    0.39
    POSITIVE LOGITS
    ინი
    0.53
     doświad
    0.51
    }:$
    0.50
    ін
    0.48
    ETIC
    0.48
    ковский
    0.47
     безпе
    0.47
    ੩
    0.47
     сертифика
    0.46
    ńskich
    0.46
    Activations Density 0.003%

    No Known Activations