© 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-65K
    4. 28192
    Prev
    Next
    INDEX
    Explanations

    creating fictional terms

    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_65k_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
    𒊩
    0.54
    getAvg
    0.51
     stret
    0.47
     wre
    0.46
    क्सन
    0.46
    গার্ড
    0.44
    )^{*}
    0.44
     την
    0.43
    コレ
    0.43
     ipotesi
    0.43
    POSITIVE LOGITS
    t
    0.67
    tail
    0.48
    There
    0.46
    logical
    0.44
    UDP
    0.44
    US
    0.44
    uda
    0.44
    hak
    0.44
    त
    0.43
    Within
    0.43
    Activations Density 0.008%

    No Known Activations