© 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. 10820
    Prev
    Next
    INDEX
    Explanations

    bullet points

    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
     to
    0.51
     inhomogeneities
    0.46
    yer
    0.46
    𝘆
    0.43
     ruining
    0.42
     imitated
    0.42
     vontade
    0.42
    사가
    0.42
     |.
    0.41
     tornou
    0.41
    POSITIVE LOGITS
     preposition
    0.47
     nChar
    0.46
     甲
    0.45
    দা
    0.44
    ול
    0.44
    льнай
    0.44
    ঃ
    0.43
    дук
    0.42
    ARIO
    0.41
    powied
    0.41
    Activations Density 0.001%

    No Known Activations