© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43776
    Prev
    Next
    INDEX
    Explanations

    striving for a goal

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

    The neuron detects goal-oriented “X for Y” phrases—verbs like aiming, shooting, striving, or trying followed by for plus a target.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \
    -2.47
     télévisée
    -1.72
     выборе
    -1.71
    裡的
    -1.69
    !”
    -1.66
    }
    -1.65
     しょう
    -1.62
    並沒有
    -1.62
    !’
    -1.54
    会的
    -1.54
    POSITIVE LOGITS
    ان
    1.58
     to
    1.55
    旆
    1.54
    ляется
    1.52
    ется
    1.48
    ться
    1.41
    休息
    1.38
    NOL
    1.35
     amines
    1.33
     isEqual
    1.31
    Activations Density 0.014%

    No Known Activations