© 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. 111457
    Prev
    Next
    INDEX
    Explanations

    transfer, advance, tribute

    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
    குடும்ப
    0.45
    utables
    0.44
    Diesel
    0.44
    箓
    0.43
    Assumption
    0.42
    Cannot
    0.42
    Comma
    0.42
    锄
    0.42
    菉
    0.42
     단순
    0.42
    POSITIVE LOGITS
     dagen
    0.45
     kaki
    0.44
    </b>
    0.44
     देशभर
    0.43
     Thar
    0.43
     जोर
    0.42
    </u>
    0.41
     fervent
    0.41
    
    0.41
     Optionen
    0.41
    Activations Density 0.008%

    No Known Activations