© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4689
    Prev
    Next
    INDEX
    Explanations

    rank, score, MAC address, speed, harm

    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
    кать
    0.51
     =-
    0.50
    𝘬
    0.48
     extré
    0.47
     "\
    0.46
     (-\
    0.45
    dokument
    0.45
    бовать
    0.45
     ಮಾಡುವ
    0.45
     fatta
    0.45
    POSITIVE LOGITS
    ש
    0.45
    שׁ
    0.42
    ні
    0.41
     married
    0.41
     futuristic
    0.41
     Derek
    0.41
    Associate
    0.41
    pur
    0.40
     announce
    0.40
     repealed
    0.40
    Activations Density 0.000%

    No Known Activations