© 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. 155683
    Prev
    Next
    INDEX
    Explanations

    speech sounds or descriptions of actions

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

    properly approached, potential barriers

    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
    îte
    0.49
    mp
    0.47
    leqq
    0.44
    nx
    0.44
    να
    0.43
    mouse
    0.42
    ί
    0.42
    name
    0.42
    ngr
    0.41
    left
    0.41
    POSITIVE LOGITS
     Vanity
    0.49
    蘅
    0.47
    赟
    0.45
     पर्सन
    0.45
     لنک
    0.44
    пикир
    0.44
    综艺
    0.44
    önt
    0.44
     नेते
    0.44
     करणाऱ्या
    0.43
    Activations Density 0.000%

    No Known Activations