© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138350
    Prev
    Next
    INDEX
    Explanations

    purchase, payment, galleries, private

    np_acts-logits-general · gemini-2.5-flash-lite

    Bank Deposits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    0.44
    },
    0.43
     hostel
    0.42
     caustic
    0.42
     last
    0.42
     (
    0.42
     devotes
    0.42
    rest
    0.41
     gazet
    0.41
     alert
    0.41
    POSITIVE LOGITS
    ಷ್ಯ
    0.49
    Etudes
    0.49
    SecurityMarks
    0.48
    僞
    0.46
    心理
    0.45
    ಙ
    0.45
     अटे
    0.45
     미술
    0.45
     Studien
    0.44
     వు
    0.44
    Activations Density 0.001%

    No Known Activations