© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 85480
    Prev
    Next
    INDEX
    Explanations

    thread safe programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    0.45
    le
    0.44
    ;
    0.43
    ຸ
    0.42
    ़
    0.40
     ponerse
    0.39
     comparatively
    0.38
    </i>
    0.38
     They
    0.38
    Comparative
    0.38
    POSITIVE LOGITS
    }^{*}=
    0.53
     zwar
    0.53
    }^{+}(
    0.52
    cartes
    0.51
    MovementControls
    0.51
     Heiz
    0.51
     wartość
    0.50
     frü
    0.49
    कता
    0.49
     früh
    0.49
    Activations Density 0.000%

    No Known Activations