© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 13459
    Prev
    Next
    INDEX
    Explanations

    value, rate, Q, D, FV

    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
     Duration
    0.43
    
    0.43
     eligibility
    0.39
     ignition
    0.39
     Current
    0.38
     PARK
    0.38
     COORDIN
    0.37
    ‐
    0.37
     Input
    0.37
     Period
    0.37
    POSITIVE LOGITS
     পরবর্ত
    0.42
    Despatx
    0.42
     विदेशों
    0.40
    aughters
    0.40
    ivatives
    0.40
    票房
    0.40
     reorganized
    0.39
    ଆ
    0.38
     সাহায
    0.38
    uffles
    0.38
    Activations Density 0.004%

    No Known Activations