© 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. 16965
    Prev
    Next
    INDEX
    Explanations

    consistent jokes content artifacts learn photo

    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
    FromResult
    0.45
    ட
    0.42
     handleSubmit
    0.42
    வர்களின்
    0.41
    istosoma
    0.41
     multiSelectList
    0.41
    ர்களின்
    0.41
     فونٹ
    0.40
    branched
    0.39
     Responder
    0.39
    POSITIVE LOGITS
    бами
    0.42
    we
    0.41
    obut
    0.39
     EXPL
    0.39
     י
    0.38
     ado
    0.38
    Conference
    0.38
    חו
    0.38
     גר
    0.38
     я
    0.38
    Activations Density 0.001%

    No Known Activations