© 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. 31-GEMMASCOPE-2-RES-262K
    7. 128355
    Prev
    Next
    INDEX
    Explanations

    selective deprotection or too complex

    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
     sensors
    0.49
     dobr
    0.48
     థ
    0.47
     sensores
    0.46
     pores
    0.45
     insurers
    0.45
     auditors
    0.44
     inventors
    0.44
     Doris
    0.43
     pies
    0.43
    POSITIVE LOGITS
    漠
    0.52
     değişken
    0.45
    muslim
    0.44
    angani
    0.42
    렇게
    0.42
    itochond
    0.42
    ☪
    0.41
    Ӏ
    0.41
     timestep
    0.41
     tràn
    0.41
    Activations Density 0.001%

    No Known Activations