© 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. 152441
    Prev
    Next
    INDEX
    Explanations

    phone numbers containing 3

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

    documentary or assisting in actions

    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
    alakip
    0.55
    𝒚
    0.47
    𝑢
    0.47
     रिक
    0.45
    en
    0.45
    𝘨
    0.45
     عدد
    0.44
    emn
    0.44
    quire
    0.44
     दक्ष
    0.44
    POSITIVE LOGITS
     frequ
    0.52
     micrograph
    0.50
     chrys
    0.49
     condensing
    0.48
    <0xA8>
    0.47
     collage
    0.47
     continuer
    0.47
    érées
    0.47
     frequented
    0.47
     endeavor
    0.46
    Activations Density 0.001%

    No Known Activations