© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 3534
    Prev
    Next
    INDEX
    Explanations

    interactions in a narrative context where choices can be made by a character.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    to some extent

    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
     最近
    0.41
     щоб
    0.37
     需要
    0.37
     Spannung
    0.37
     భాగ
    0.35
     iterable
    0.35
     删除
    0.35
     上
    0.34
     然后
    0.34
     хочу
    0.34
    POSITIVE LOGITS
    ppling
    0.48
    ge
    0.47
    ppled
    0.47
    지
    0.47
    ffee
    0.46
     be
    0.42
    ilers
    0.41
    pples
    0.40
    ס
    0.40
    pless
    0.40
    Activations Density 0.197%

    No Known Activations