© 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. 55431
    Prev
    Next
    INDEX
    Explanations

    credit history

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

    conglomerate and control

    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
    CDN
    0.55
    at
    0.51
    Animation
    0.51
     infra
    0.50
    Flare
    0.48
    Fps
    0.48
    Logo
    0.47
    k
    0.47
    Locations
    0.47
    ACS
    0.47
    POSITIVE LOGITS
     conglomer
    0.46
    꽉
    0.45
    뻣
    0.43
     conglomerate
    0.41
     playoff
    0.41
     Steam
    0.41
     باقی
    0.40
     needless
    0.40
     قبض
    0.40
    兢
    0.40
    Activations Density 0.000%

    No Known Activations