© 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. 135426
    Prev
    Next
    INDEX
    Explanations

    ethical business or supporting practitioners

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

    mission-critical strategies

    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
     poema
    0.43
     electrolyte
    0.43
     FB
    0.42
    ဖ
    0.42
    板
    0.42
     breve
    0.41
     resistor
    0.41
    了两
    0.41
     pericard
    0.41
     C
    0.40
    POSITIVE LOGITS
    !),
    0.59
    🏘
    0.55
    Unlock
    0.55
    Blockchain
    0.53
    Reconnect
    0.53
    🥳
    0.52
    🧐
    0.49
     לג
    0.49
     світу
    0.48
    Staying
    0.48
    Activations Density 0.000%

    No Known Activations