© 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. 36327
    Prev
    Next
    INDEX
    Explanations

    prevents rank, talk about, four astronauts

    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
    􀂾
    0.43
    elor
    0.41
     facade
    0.41
    <unused90>
    0.40
    an
    0.40
    oa
    0.40
    χου
    0.40
    adon
    0.39
    umls
    0.39
    isan
    0.39
    POSITIVE LOGITS
    ੲ
    0.50
     स्वत
    0.45
     sleepers
    0.45
    гідно
    0.44
    Salir
    0.43
     Дмитри
    0.43
     देसी
    0.43
     identique
    0.43
     harder
    0.42
    ئ
    0.42
    Activations Density 0.004%

    No Known Activations