© 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. 4822
    Prev
    Next
    INDEX
    Explanations

    evaluative metering at

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

    options

    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
    akaranam
    0.40
    Introduceti
    0.37
     ünlü
    0.37
    apayati
    0.37
     খাঁর
    0.37
    㙋
    0.37
     అనేది
    0.37
     בשנת
    0.36
    oelectronic
    0.36
     setattr
    0.36
    POSITIVE LOGITS
    7
    0.42
      
    0.39
    LOW
    0.39
     livestream
    0.37
     vetted
    0.37
    甜
    0.36
     tailored
    0.36
     Patreon
    0.36
     midweek
    0.36
     FaceTime
    0.36
    Activations Density 0.202%

    No Known Activations