© 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. 36692
    Prev
    Next
    INDEX
    Explanations

    place of origin

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

    many of which, legend says, edition has, abandoned AR, designer quality

    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
    ።
    0.48
    “.
    0.47
    During
    0.47
    .”
    0.46
    clientes
    0.46
    될
    0.46
    。
    0.45
    }$.
    0.45
    मैं
    0.45
     definitively
    0.44
    POSITIVE LOGITS
     water
    0.56
     vowel
    0.52
    water
    0.51
     aquifer
    0.50
     mineral
    0.49
     ItemStack
    0.48
    髮
    0.45
     सांगित
    0.44
     Anch
    0.44
     armature
    0.44
    Activations Density 0.000%

    No Known Activations