© 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. 196474
    Prev
    Next
    INDEX
    Explanations

    before or after specific actions

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

    weight gain and vore themes

    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
    ſed
    0.44
    ἱ
    0.41
     should
    0.41
     mortg
    0.41
     gages
    0.41
    লেখা
    0.41
     Males
    0.40
     loan
    0.40
    亦
    0.40
    یشہ
    0.40
    POSITIVE LOGITS
     குரு
    0.50
    hör
    0.46
     (“
    0.45
     ऑर्गे
    0.44
     débil
    0.43
    <unused95>
    0.42
     পোকামাকড়
    0.42
     वेरिएबल
    0.42
     வெளியே
    0.42
    เสนอ
    0.42
    Activations Density 0.001%

    No Known Activations