© 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. 33120
    Prev
    Next
    INDEX
    Explanations

    approximately, storm, sense, own, name

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

    common descriptions and welcome greetings

    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
    rich
    0.46
    our
    0.43
    9
    0.42
    tronic
    0.41
    hunt
    0.41
    susp
    0.41
    listed
    0.40
    pec
    0.40
     contient
    0.40
    flu
    0.40
    POSITIVE LOGITS
     імені
    0.50
    解释
    0.46
    鞋
    0.45
     secretário
    0.45
    节日
    0.44
     鞋
    0.44
     révolution
    0.44
     япон
    0.44
     Japanese
    0.42
    Japanese
    0.42
    Activations Density 0.000%

    No Known Activations