© 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. 160310
    Prev
    Next
    INDEX
    Explanations

    inner conduit

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

    past tense, material, PCB, covid, tea, during, local

    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
    únior
    0.56
    *",
    0.48
    PersonalInfo
    0.48
    KeyboardView
    0.48
    ycopg
    0.46
    变量
    0.46
    年中
    0.46
    myCollision
    0.45
    િતા
    0.45
    ScienceStudent
    0.44
    POSITIVE LOGITS
     sleepy
    0.47
     daylight
    0.45
     tirer
    0.45
    </em>
    0.44
     kanya
    0.44
     keine
    0.44
     denke
    0.44
     einem
    0.44
    ktional
    0.44
     razlik
    0.43
    Activations Density 0.000%

    No Known Activations