© 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. 123488
    Prev
    Next
    INDEX
    Explanations

    creative problem-solving

    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
    ahit
    0.45
    妝
    0.45
    ánica
    0.44
     ट्रॉपिकल
    0.44
    <0x90>
    0.44
    ար
    0.43
    ablement
    0.43
    ेश
    0.42
     SEK
    0.42
    প
    0.42
    POSITIVE LOGITS
     shows
    0.48
     rumors
    0.47
     hard
    0.47
     personnel
    0.46
     vinaig
    0.46
     vapors
    0.46
     harbors
    0.46
     army
    0.45
     rents
    0.45
     sınır
    0.45
    Activations Density 0.001%

    No Known Activations