© 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. 27231
    Prev
    Next
    INDEX
    Explanations

    short, often, keep, latest, green

    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
    emaakt
    0.50
    台灣
    0.43
    셸
    0.40
    एयर
    0.37
    ዴት
    0.36
     आखिरकार
    0.36
     लाइसेंस
    0.35
     جمهوری
    0.35
     بہانہ
    0.35
    籐
    0.35
    POSITIVE LOGITS
    </h3>
    0.43
     resulted
    0.42
    </h5>
    0.37
     Eint
    0.37
     averiguar
    0.36
     miserably
    0.36
    くれました
    0.36
     posteriores
    0.36
     prepend
    0.36
    Remainder
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.