© 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. 64972
    Prev
    Next
    INDEX
    Explanations

    insurance, quickly, resources, bit

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

    cybersecurity, frameworks, meanings, policing

    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
    ponsors
    0.46
    zhou
    0.44
    ;*/
    0.43
    ning
    0.42
    -
    0.42
    semble
    0.41
     responsible
    0.41
     માટે
    0.40
    =
    0.40
    🇦
    0.40
    POSITIVE LOGITS
     잠깐
    0.45
     wartość
    0.44
     외
    0.43
     증가
    0.42
     요소
    0.42
    엿
    0.42
     carcass
    0.41
     마치
    0.41
    תר
    0.41
     turret
    0.41
    Activations Density 0.000%

    No Known Activations