© 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. 163117
    Prev
    Next
    INDEX
    Explanations

    "The" followed by a noun phrase

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

    recognizing specific concepts or items

    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
    احث
    0.60
    ㄞ
    0.54
    ATORS
    0.53
    }^{+}$,
    0.53
    cted
    0.51
     अराउंड
    0.51
    ulously
    0.49
    迲
    0.49
    ()==
    0.48
    ಿಸಿದ್ದ
    0.48
    POSITIVE LOGITS
     Ninja
    0.46
     Campe
    0.45
     Test
    0.45
     бой
    0.45
     parody
    0.45
     spectacle
    0.44
     banheiro
    0.44
     payment
    0.44
    ninja
    0.44
     pré
    0.43
    Activations Density 0.000%

    No Known Activations