© 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. 193684
    Prev
    Next
    INDEX
    Explanations

    free and calm

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

    you must

    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
     triglycer
    0.46
    ರ್ಧ
    0.44
     तथ
    0.44
     expediency
    0.44
    窘
    0.44
     crappy
    0.43
     едно
    0.43
     decryption
    0.43
    benzoyl
    0.43
     सिम
    0.42
    POSITIVE LOGITS
    ί
    0.55
    imu
    0.52
    í
    0.52
    ī
    0.51
    ou
    0.48
    iff
    0.48
    olo
    0.48
    î
    0.48
    ied
    0.47
    ור
    0.47
    Activations Density 0.000%

    No Known Activations