© 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. 30334
    Prev
    Next
    INDEX
    Explanations

    moving beyond, from figures, after you

    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
     futile
    0.41
    льній
    0.41
    лга
    0.39
    }^{*}=
    0.39
    ción
    0.39
     caméra
    0.38
    ത്തിയ
    0.37
     法
    0.37
    ጣት
    0.37
    }=-
    0.37
    POSITIVE LOGITS
    6
    0.62
    9
    0.61
    7
    0.59
    2
    0.54
    8
    0.50
    3
    0.47
    5
    0.47
    াফ
    0.45
     ekonomik
    0.42
    对应
    0.42
    Activations Density 0.001%

    No Known Activations