© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9248
    Prev
    Next
    INDEX
    Explanations

    walls

    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_16_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
     ఇలా
    0.38
     മ
    0.36
    适合
    0.36
    إ
    0.35
    cigarettes
    0.34
     గా
    0.34
    temperatur
    0.33
     אם
    0.33
    tså
    0.33
    ש
    0.33
    POSITIVE LOGITS
     mewn
    0.38
     ontology
    0.37
     wiki
    0.36
     spleen
    0.36
    *
    0.35
     coop
    0.35
     jurisprudence
    0.35
     anthropology
    0.35
     intracranial
    0.35
    NL
    0.34
    Activations Density 0.000%

    No Known Activations