© 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. 168855
    Prev
    Next
    INDEX
    Explanations

    mimic, notice, remembering, enjoying, secretive

    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
    int
    0.50
    ဝ်
    0.48
    :]
    0.47
    id
    0.45
    ong
    0.45
    i
    0.44
    ing
    0.44
    iam
    0.44
    an
    0.44
    і
    0.44
    POSITIVE LOGITS
     Lihat
    0.55
     Нужно
    0.53
    ্লে
    0.51
     හැ
    0.50
     ඉතා
    0.50
     ана
    0.50
     موس
    0.48
     нужно
    0.46
     दुप
    0.46
    dichlor
    0.45
    Activations Density 0.003%

    No Known Activations