© 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-65K
    7. 45406
    Prev
    Next
    INDEX
    Explanations

    automation, feeding, self, absent

    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
     deducting
    0.47
     documenting
    0.44
     thermos
    0.43
    ,【
    0.43
    ;</
    0.42
    .’”
    0.42
     ammo
    0.41
     অন্যদিকে
    0.41
     supernatant
    0.41
     ಭಾವ
    0.41
    POSITIVE LOGITS
     वीक
    0.44
     Rather
    0.44
    Ма
    0.43
     جدید
    0.43
    为了
    0.43
     Hercegov
    0.43
     Besuch
    0.42
     Часто
    0.42
    י
    0.42
    یر
    0.41
    Activations Density 0.012%

    No Known Activations