© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35147
    Prev
    Next
    INDEX
    Explanations

    variable and configuration identifiers

    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_40_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
     utter
    0.41
     utterly
    0.40
     אי
    0.40
    maxcdn
    0.38
     এক
    0.37
    াগর
    0.36
     ἔ
    0.35
    اً
    0.34
    ابية
    0.34
    ро
    0.34
    POSITIVE LOGITS
     APP
    0.40
     AO
    0.38
    APS
    0.38
     AW
    0.35
     vro
    0.34
    િજા
    0.34
     AD
    0.34
     ADS
    0.33
    NFT
    0.33
     Evalu
    0.33
    Activations Density 0.056%

    No Known Activations