© 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. 137538
    Prev
    Next
    INDEX
    Explanations

    subject followed by verb

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

    Presenting, scaling, attention

    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
     on
    0.49
    .
    0.45
     rom
    0.43
    -
    0.40
     von
    0.40
    lof
    0.39
    saa
    0.38
     beam
    0.37
    shu
    0.37
     ام
    0.36
    POSITIVE LOGITS
    फॉर्म
    0.45
     வால்பேப்ப
    0.45
    ÃO
    0.44
    वैसे
    0.44
    感じです
    0.44
    ರಿಸ
    0.42
    послед
    0.41
    ה
    0.41
    𝗮
    0.41
    ？」
    0.41
    Activations Density 0.526%

    No Known Activations