© 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. 244202
    Prev
    Next
    INDEX
    Explanations

    specific entity descriptions

    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
    ष्क
    0.49
     ያስ
    0.48
    ве
    0.45
    ві
    0.45
    𝚛
    0.45
    忶
    0.44
    がか
    0.44
     ejection
    0.44
     coordenadas
    0.44
    י
    0.43
    POSITIVE LOGITS
     AZ
    0.46
    တို့ကို
    0.44
    Multiline
    0.44
    RELATIVA
    0.43
     sessionId
    0.42
     MACH
    0.42
    dives
    0.42
    ódio
    0.42
    MK
    0.41
    ಿದ್ದೇವೆ
    0.41
    Activations Density 0.000%

    No Known Activations