© 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. 42523
    Prev
    Next
    INDEX
    Explanations

    follow or comply with rules

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

    violates content policy

    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
     UNIX
    0.40
    data
    0.39
     ডা
    0.39
    ).__
    0.39
     data
    0.39
     erfolgt
    0.38
     Connecticut
    0.38
     DataFrame
    0.38
     elapsed
    0.38
     rosa
    0.38
    POSITIVE LOGITS
    SearchView
    0.54
    ImageView
    0.52
    Giải
    0.49
    糇
    0.47
     অশ্লীল
    0.47
     selfie
    0.46
    JPG
    0.45
    Verify
    0.44
     গর্
    0.43
    FirebaseAuth
    0.43
    Activations Density 0.000%

    No Known Activations