© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1898
    Prev
    Next
    INDEX
    Explanations

    of/for followed by another/invalid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ה
    0.55
     pectoral
    0.53
     livre
    0.48
    ע
    0.47
     за
    0.46
    ه
    0.46
     pied
    0.45
    ţia
    0.45
    зи
    0.44
     которого
    0.44
    POSITIVE LOGITS
     Aware
    0.46
    grade
    0.46
     erhöht
    0.44
    orsk
    0.44
    aksha
    0.44
    )}>
    0.43
    gates
    0.43
    t
    0.43
    nYou
    0.42
    ാവ
    0.42
    Activations Density 0.000%

    No Known Activations