© 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. 124218
    Prev
    Next
    INDEX
    Explanations

    final vote, CPD Accreditation

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

    recording, capture, responding

    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
     articolo
    0.51
    '};
    0.50
     معين
    0.49
     Scores
    0.48
     Transcript
    0.48
    "};
    0.47
     محیط
    0.46
     StringBuffer
    0.46
    เฉพาะ
    0.46
    '});
    0.46
    POSITIVE LOGITS
    éph
    0.46
    essentially
    0.46
     हां
    0.44
    orant
    0.43
    ्टर
    0.43
    ing
    0.41
    आपका
    0.41
    can
    0.41
    ég
    0.41
    ười
    0.41
    Activations Density 0.002%

    No Known Activations