© 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. 93808
    Prev
    Next
    INDEX
    Explanations

    strong modifications and systems

    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
     filters
    0.46
     radish
    0.43
    غ
    0.42
     uniquely
    0.41
     unary
    0.41
     filtration
    0.40
     hydros
    0.40
     싫
    0.40
    pessoa
    0.39
     channels
    0.39
    POSITIVE LOGITS
     अवेलेबल
    0.52
    💂
    0.52
    eyen
    0.46
    aleigh
    0.46
    eye
    0.45
     Mary
    0.45
     бре
    0.44
    拿下
    0.44
     Underwood
    0.43
     નિર્ણય
    0.43
    Activations Density 0.005%

    No Known Activations