Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 26642
    Prev
    Next
    INDEX
    Explanations

    descriptive initial words

    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
     yú
    0.45
     এলাক
    0.41
     emptied
    0.40
    odeling
    0.40
    อบ
    0.39
    gehend
    0.39
    诓
    0.39
     delightfully
    0.39
     beide
    0.38
    ná
    0.38
    POSITIVE LOGITS
    Joseph
    0.44
     जिनको
    0.44
     Estimates
    0.44
     Collo
    0.44
     necesita
    0.43
     insolvency
    0.43
     Estimate
    0.42
     ESTIM
    0.42
     PhoneNumber
    0.42
    𝓶
    0.42
    Activations Density 0.002%

    No Known Activations