© 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. 40-GEMMASCOPE-2-RES-262K
    7. 20830
    Prev
    Next
    INDEX
    Explanations

    technical terms, often followed by context

    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_40_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
     hydrodynamic
    0.37
     값이
    0.37
    傑
    0.36
    equalTo
    0.35
     Failure
    0.35
    ).)
    0.35
     घाल
    0.35
     изготовления
    0.35
     beziehen
    0.34
     produce
    0.34
    POSITIVE LOGITS
    পুর
    0.44
    icollis
    0.41
    ⓓ
    0.41
    áne
    0.40
     Primero
    0.38
    prem
    0.38
    债
    0.38
     imagined
    0.38
    vline
    0.38
     necesariamente
    0.38
    Activations Density 0.000%

    No Known Activations