© 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. 54264
    Prev
    Next
    INDEX
    Explanations

    schedule or list separator

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

    Lovers, Lucifer, Production, Mechanism

    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
     argumentation
    0.49
    }-(\
    0.48
    spraak
    0.47
    បង្ហ
    0.46
     perv
    0.45
     แจ
    0.44
     মানিক
    0.44
    ເຂົ້າ
    0.44
    िक्स
    0.43
    షన్
    0.43
    POSITIVE LOGITS
    ’
    0.48
    '
    0.47
    </td>
    0.46
    ᴿ
    0.44
     Mixer
    0.43
     manufacturer
    0.41
     번
    0.41
    Production
    0.41
    Workspace
    0.41
    Primer
    0.41
    Activations Density 0.000%

    No Known Activations