© 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. 40-GEMMASCOPE-2-RES-262K
    7. 34744
    Prev
    Next
    INDEX
    Explanations

    Insta, instatravel, instafood

    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
     considere
    0.40
    ahlen
    0.39
    opadhyay
    0.39
    バリー
    0.39
    Periph
    0.38
     })_{
    0.38
    AlH
    0.38
    െയുള്ള
    0.37
    Mits
    0.37
    췌
    0.37
    POSITIVE LOGITS
     Inst
    0.75
     inst
    0.66
     इंस्ट
    0.59
    Inst
    0.59
     INST
    0.55
     Instinct
    0.54
    inst
    0.51
     instantiation
    0.50
    INST
    0.48
     Insta
    0.47
    Activations Density 0.005%

    No Known Activations