© 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. 76431
    Prev
    Next
    INDEX
    Explanations

    certified copiesFriedman never

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

    underlying responsibility

    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
    ത്
    0.45
     flaps
    0.43
    iet
    0.43
     mottled
    0.42
     pours
    0.42
    ïs
    0.42
    白い
    0.40
    唾
    0.40
    oire
    0.40
     bordering
    0.40
    POSITIVE LOGITS
     transformação
    0.53
     রাস্তায়
    0.52
     hoặc
    0.49
     এইরূপ
    0.49
     veya
    0.48
     Mechanics
    0.46
    还是要
    0.46
     किंवा
    0.45
     হইয়াছিল
    0.45
     родился
    0.45
    Activations Density 0.000%

    No Known Activations