© 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. 153854
    Prev
    Next
    INDEX
    Explanations

    places, story, you, wondering, arrested

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

    Listings and IQ Scores

    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
    칸
    0.55
    Tt
    0.49
    Georges
    0.49
    ≻
    0.48
    Jwt
    0.47
    τ
    0.46
    პ
    0.46
    HighScore
    0.45
    jumlah
    0.44
    Philippe
    0.44
    POSITIVE LOGITS
     podían
    0.52
     zwischen
    0.49
    爱好
    0.48
     pueden
    0.46
     mogą
    0.46
    疏
    0.46
     correspondió
    0.45
    面的
    0.45
     между
    0.45
     வடக்கு
    0.45
    Activations Density 0.000%

    No Known Activations