© 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. 195449
    Prev
    Next
    INDEX
    Explanations

    human, skin, stream, million, capture, texture, soon

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

    Queens Expressway, smell incredible

    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
     关于
    0.50
     cât
    0.47
    _);
    0.46
     concreta
    0.46
     coi
    0.45
     metodo
    0.45
     konkrét
    0.45
    থানি
    0.44
     quanto
    0.43
     ponder
    0.43
    POSITIVE LOGITS
    너지
    0.53
     Speakers
    0.50
     अकेले
    0.47
    衙
    0.47
     हथियार
    0.46
     Anglic
    0.46
    อนุ
    0.45
    icking
    0.45
     Emotions
    0.44
    лам
    0.44
    Activations Density 0.001%

    No Known Activations