© 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. 113200
    Prev
    Next
    INDEX
    Explanations

    dumpster materials disposal

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

    introducing context or conditions

    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
     transcends
    0.47
     khái
    0.43
    ╋
    0.43
     spanned
    0.42
     imagined
    0.41
     شغ
    0.40
     transcend
    0.40
    이었다
    0.40
    +
    0.40
     blocker
    0.39
    POSITIVE LOGITS
    ರ್ಭ
    0.45
    raina
    0.45
    ider
    0.43
    ၿ
    0.43
    SA
    0.42
    ayan
    0.42
    েনে
    0.42
     काउंस
    0.42
     Continuing
    0.41
     Offences
    0.41
    Activations Density 0.000%

    No Known Activations