© 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. 13423
    Prev
    Next
    INDEX
    Explanations

    wasn't like the other

    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
    ceram
    0.48
    HEAT
    0.46
    Mou
    0.46
    餘
    0.46
    Kul
    0.46
    imų
    0.45
    Kuch
    0.44
    Innovation
    0.44
    지
    0.44
    uiu
    0.43
    POSITIVE LOGITS
     Chico
    0.50
     the
    0.48
     Lessor
    0.46
     doing
    0.45
     Tahoma
    0.45
     Habe
    0.45
     vutto
    0.45
     ఇంటి
    0.44
     USB
    0.42
     Adidas
    0.42
    Activations Density 0.007%

    No Known Activations