© 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-262K
    7. 18276
    Prev
    Next
    INDEX
    Explanations

    login and signup forms

    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
     birth
    0.38
    :**
    0.37
    ità
    0.37
    тті
    0.36
     Gregorian
    0.36
    𝑡
    0.36
    ”:
    0.36
    éf
    0.36
     چکا
    0.36
     Doppler
    0.36
    POSITIVE LOGITS
     ogrod
    0.43
     niezb
    0.40
    Forgotten
    0.39
     promot
    0.37
     आम्
    0.36
    樖
    0.36
    getBlueTeam
    0.36
     alkene
    0.36
     glories
    0.36
    ഞ്
    0.35
    Activations Density 0.004%

    No Known Activations