© 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. 225948
    Prev
    Next
    INDEX
    Explanations

    blockbuster movies and football clubs

    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
     Rochester
    0.49
    comstock
    0.46
     जिज्ञासा
    0.45
    糗
    0.43
     magistrate
    0.40
    家電
    0.40
    轂
    0.40
    сион
    0.40
     জরি
    0.40
     मोहो
    0.40
    POSITIVE LOGITS
    Franco
    0.48
    Transparent
    0.45
     Franco
    0.44
     transparent
    0.43
     Colombian
    0.43
     ऊ
    0.43
     Tox
    0.42
    Fold
    0.42
    হ্ন
    0.42
     Neymar
    0.41
    Activations Density 0.018%

    No Known Activations