© 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. 3957
    Prev
    Next
    INDEX
    Explanations

    Car, Language, Raspberry Pi, Water, atoms

    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
    ûn
    0.42
     সাইফুল
    0.40
     hoof
    0.39
     confidentiality
    0.38
     მთავ
    0.38
    Verse
    0.38
     apod
    0.38
    筊
    0.38
     syst
    0.38
    <0xB6>
    0.38
    POSITIVE LOGITS
    at
    0.49
     Aubrey
    0.48
     Tochter
    0.45
     откры
    0.41
    Equity
    0.40
    pinned
    0.40
    ierta
    0.39
    าะ
    0.39
    ugg
    0.38
     महत्त्वा
    0.38
    Activations Density 0.022%

    No Known Activations