© 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. 120181
    Prev
    Next
    INDEX
    Explanations

    network port definitions

    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
    ход
    0.48
    हर
    0.47
     fus
    0.44
    ხვევ
    0.43
    ሱን
    0.43
    無料
    0.42
     isos
    0.39
    ³/
    0.39
    idin
    0.39
    хий
    0.39
    POSITIVE LOGITS
     Zusammenarbeit
    0.43
    ımız
    0.40
     pseudonym
    0.38
    ன்படி
    0.38
    ReadKey
    0.37
     équipe
    0.37
     współpracy
    0.36
     Système
    0.36
    zIndex
    0.36
     réfé
    0.34
    Activations Density 0.000%

    No Known Activations