© 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-262K
    4. 3098
    Prev
    Next
    INDEX
    Explanations

    questions or `TypeError`

    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
     PAID
    0.48
    ל
    0.48
    洱
    0.46
    ாட்டு
    0.46
    ла
    0.46
    น์
    0.46
     histórias
    0.46
    Computation
    0.46
    观众
    0.45
     понять
    0.45
    POSITIVE LOGITS
     $\
    0.50
     I
    0.47
    }\
    0.46
     Le
    0.45
    tab
    0.45
     She
    0.44
    the
    0.43
    luc
    0.43
     R
    0.42
    vs
    0.42
    Activations Density 0.000%

    No Known Activations