© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 43971
    Prev
    Next
    INDEX
    Explanations

    sets immediate information

    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
     typically
    0.48
     children
    0.47
     commonly
    0.47
     usually
    0.45
     সাধারণত
    0.44
     prev
    0.43
     g
    0.42
     reusable
    0.42
     r
    0.42
     D
    0.41
    POSITIVE LOGITS
     факт
    0.61
     unapolog
    0.55
     суть
    0.53
     совокуп
    0.51
    事実
    0.50
     никакой
    0.49
     биографи
    0.48
     무엇
    0.48
     аспек
    0.48
    <unused512>
    0.48
    Activations Density 0.007%

    No Known Activations