© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    punctuation and starting words

    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
     relevancia
    0.25
     decryption
    0.24
    📨
    0.23
    Plist
    0.22
     pathophys
    0.22
    inl
    0.22
     quantidades
    0.22
     syndromes
    0.21
     fanbase
    0.21
    StarGo
    0.21
    POSITIVE LOGITS
     ਰ
    0.29
     Α
    0.29
     Архів
    0.27
    ↵
    0.27
     M
    0.27
     R
    0.27
     The
    0.26
     Rajasthan
    0.26
     Cafe
    0.26
     미국
    0.26
    Activations Density 0.194%

    No Known Activations