© 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. 5647
    Prev
    Next
    INDEX
    Explanations

    subspecies and synonyms

    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
    gene
    0.39
     limpeza
    0.37
     defec
    0.37
    練
    0.37
    macos
    0.36
     подарок
    0.36
    lysninger
    0.36
    त्याने
    0.36
     информации
    0.35
    情報
    0.35
    POSITIVE LOGITS
     variously
    0.45
    が集
    0.45
     subgroups
    0.43
    :,
    0.41
     πολλ
    0.41
     boomers
    0.41
     totals
    0.40
     원하는
    0.39
     మొత్త
    0.38
     assortment
    0.38
    Activations Density 0.000%

    No Known Activations