© 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. 221817
    Prev
    Next
    INDEX
    Explanations

    pray for

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

    sentences, anything, contexts

    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
     esper
    0.49
     goed
    0.44
    ній
    0.43
    OTP
    0.43
    เสมอ
    0.42
    ิ้ง
    0.42
    EOF
    0.41
    <0xA9>
    0.40
     VALUES
    0.39
    Esper
    0.39
    POSITIVE LOGITS
     ໃນ
    0.60
     PPAR
    0.57
     Phang
    0.57
     ventricular
    0.52
    łach
    0.52
     Findings
    0.51
     வந்து
    0.49
     முறை
    0.49
     findings
    0.49
     Hollow
    0.48
    Activations Density 0.000%

    No Known Activations