© 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. 154242
    Prev
    Next
    INDEX
    Explanations

    appreciate or like

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

    price point

    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
     غالب
    0.44
    olphe
    0.43
     solcher
    0.43
     нав
    0.40
     Tenn
    0.39
     радо
    0.39
    ınız
    0.39
     `
    0.38
     आपका
    0.38
     స్థ
    0.38
    POSITIVE LOGITS
    찜
    0.52
    biology
    0.51
    𝔱
    0.46
    Brazilian
    0.45
    냥
    0.44
    Ideas
    0.44
     idée
    0.44
     ideias
    0.43
     biología
    0.43
    نیٹ
    0.43
    Activations Density 0.007%

    No Known Activations