© 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. 200073
    Prev
    Next
    INDEX
    Explanations

    service center, schools, news, parent, accommodation

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

    regenerate limbs

    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
    らの
    0.55
    らは
    0.55
    ას
    0.53
     zahl
    0.46
    링
    0.46
    差別
    0.46
    らす
    0.45
     ച
    0.45
     언급
    0.45
    粈
    0.44
    POSITIVE LOGITS
    meter
    0.51
    hspace
    0.51
    pinimg
    0.50
    favorite
    0.50
    luck
    0.48
    fast
    0.48
    Properties
    0.48
    paper
    0.47
     metast
    0.47
    legged
    0.47
    Activations Density 0.000%

    No Known Activations