© 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. 11542
    Prev
    Next
    INDEX
    Explanations

    apart associated, use of

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

    goals and arguments

    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
     mely
    0.50
     apni
    0.50
     અન્ય
    0.49
     ਨ
    0.48
     adorn
    0.46
     işlemler
    0.46
     apna
    0.46
     ടെ
    0.46
     புதிய
    0.45
     ajal
    0.44
    POSITIVE LOGITS
    念
    0.47
    察
    0.46
    구요
    0.42
    宗
    0.40
    туи
    0.39
    స్తోంది
    0.39
    遥
    0.39
    멈
    0.38
    ירה
    0.38
     философ
    0.38
    Activations Density 0.000%

    No Known Activations