© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    contextualizing `everything 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_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
     कैलकु
    0.56
    us
    0.53
    ourcen
    0.51
     न्यूमेर
    0.50
    clientsdetails
    0.49
    秥
    0.48
    paysys
    0.48
    োপুরি
    0.47
    有多
    0.47
     ಡಿ
    0.46
    POSITIVE LOGITS
     –
    0.61
    .’
    0.51
     goût
    0.51
     distill
    0.49
    ’
    0.49
    می
    0.49
     teria
    0.49
    み
    0.48
     contempl
    0.48
     tableware
    0.46
    Activations Density 0.001%

    No Known Activations