© 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. 164621
    Prev
    Next
    INDEX
    Explanations

    intention to, also for, go forward, third party

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

    local, image, calibration, source

    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
    )”
    0.50
    ;.
    0.49
    :.
    0.46
     巻
    0.44
     உடன்
    0.44
    .​​
    0.44
    :”
    0.43
    ֖
    0.43
    _=
    0.43
    thisStudent
    0.42
    POSITIVE LOGITS
     Astral
    0.50
    光学
    0.49
    مركز
    0.45
     southeastern
    0.44
     technically
    0.44
    uva
    0.42
     Ragnar
    0.42
     stratég
    0.42
     astron
    0.42
    southern
    0.41
    Activations Density 0.000%

    No Known Activations