© 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. 188895
    Prev
    Next
    INDEX
    Explanations

    common preceding/following word pairs

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

    Calculate the

    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
    mera
    0.50
    puri
    0.49
    ఐ
    0.47
    contentType
    0.46
    gate
    0.45
     그러니까
    0.45
     sufficiently
    0.44
    phe
    0.44
    mare
    0.44
     বললো
    0.44
    POSITIVE LOGITS
    к
    0.52
     radiative
    0.50
     radiographic
    0.48
    ک
    0.48
    ΟΥ
    0.47
    ОВО
    0.47
     rnd
    0.46
     studie
    0.46
     radiators
    0.46
     risc
    0.45
    Activations Density 0.000%

    No Known Activations