© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3676
    Prev
    Next
    INDEX
    Explanations

    method, tester, sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    antai
    1.62
    8
    1.56
    7
    1.52
     Laplacian
    1.49
    liqu
    1.49
    lique
    1.47
    imeo
    1.46
    alski
    1.43
     resell
    1.40
    ilibre
    1.39
    POSITIVE LOGITS
     Methode
    1.39
     Marker
    1.25
     Tester
    1.25
     Method
    1.25
     Rat
    1.20
     (£
    1.17
    Ez
    1.16
    Ư
    1.15
    Method
    1.14
     Methoden
    1.13
    Activations Density 0.068%

    No Known Activations