© 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. 206951
    Prev
    Next
    INDEX
    Explanations

    hybrid cable

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

    chemical terms and entities

    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
    _*
    0.47
    ?]
    0.45
    </footer>
    0.44
    ?<
    0.44
    </sup>
    0.42
     değ
    0.42
    *
    0.42
    ēc
    0.42
    écution
    0.42
     Tecnología
    0.42
    POSITIVE LOGITS
     cifra
    0.46
    ytte
    0.43
     maxima
    0.43
    illions
    0.42
     divergences
    0.42
    Naissance
    0.42
    itha
    0.41
     voler
    0.41
     synthesis
    0.40
    ย์
    0.40
    Activations Density 0.000%

    No Known Activations