© 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. 5996
    Prev
    Next
    INDEX
    Explanations

    Python code, code structures

    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
    hanti
    0.37
     représenter
    0.35
     Jérôme
    0.32
     réalité
    0.31
    溽
    0.31
     publicité
    0.30
     Elektrokhimiya
    0.30
     Anspr
    0.30
     vattum
    0.30
     AcOH
    0.29
    POSITIVE LOGITS
    ↵
    0.41
    1
    0.35
    4
    0.35
    7
    0.33
    2
    0.33
    Case
    0.33
    Partition
    0.32
     started
    0.31
    5
    0.31
    Creo
    0.31
    Activations Density 0.059%

    No Known Activations