© 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. 4599
    Prev
    Next
    INDEX
    Explanations

    "that import" or code snippets

    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
     tồn
    1.52
    represent
    1.51
     Entities
    1.44
    6
    1.40
     Kohn
    1.39
     Belong
    1.39
    false
    1.38
    isRequired
    1.38
    entities
    1.36
     Linden
    1.36
    POSITIVE LOGITS
     daddy
    1.37
     dinner
    1.34
     semana
    1.27
     (=
    1.26
    chst
    1.20
    organizzazione
    1.19
     منصوبہ
    1.19
     pewno
    1.18
    lly
    1.18
     semaine
    1.17
    Activations Density 0.025%

    No Known Activations