© 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. 56998
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    †
    0.46
    Reg
    0.44
    اں
    0.43
     则
    0.42
     restricts
    0.42
     kwenye
    0.41
    Mand
    0.40
    ச்
    0.40
    브
    0.40
    unc
    0.39
    POSITIVE LOGITS
     psicología
    0.44
     psicol
    0.43
     thermodynamics
    0.43
     भाग्य
    0.42
     axi
    0.42
     ভাগ্যবান
    0.42
     uzun
    0.41
     psicologia
    0.41
     unsolved
    0.40
     психологи
    0.40
    Activations Density 0.030%

    No Known Activations